Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4972 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0024. Min Range: -5.0024
Max Act: 5.0024. Min Act: -0.1700
Data Index: 7721194 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0024. Min Range: -5.0024
Max Act: 5.0024. Min Act: -0.1700
Data Index: 1138790 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.9711. Min Act: -0.1700
Data Index: 1692873 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.9711. Min Act: -0.1700
Data Index: 7377297 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.8774. Min Act: -0.1700
Data Index: 5036866 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.9086. Min Act: -0.1700
Data Index: 8720388 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.8461. Min Act: -0.1700
Data Index: 1629252 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.8149. Min Act: -0.1700
Data Index: 1785845 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.8149. Min Act: -0.1700
Data Index: 4045271 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.8149. Min Act: -0.1700
Data Index: 1341659 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.8461. Min Act: -0.1700
Data Index: 6829047 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.8149. Min Act: -0.1700
Data Index: 8331073 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.7836. Min Act: -0.1700
Data Index: 1762393 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.7836. Min Act: -0.1700
Data Index: 724040 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.7836. Min Act: -0.1700
Data Index: 39452 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.7524. Min Act: -0.1700
Data Index: 8314054 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.7524. Min Act: -0.1700
Data Index: 693813 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.7524. Min Act: -0.1700
Data Index: 4203164 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.7211. Min Act: -0.1700
Data Index: 4659827 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0024. Min Range: -5.0024
Max Act: 4.7211. Min Act: -0.1700
Data Index: 5478247 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19